Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "ARM:

   - A couple of fixes when handling an exception while a SError has
     been delivered

   - Workaround for Cortex-A510's single-step erratum

  RISC-V:

   - Make CY, TM, and IR counters accessible in VU mode

   - Fix SBI implementation version

  x86:

   - Report deprecation of x87 features in supported CPUID

   - Preparation for fixing an interrupt delivery race on AMD hardware

   - Sparse fix

  All except POWER and s390:

   - Rework guest entry code to correctly mark noinstr areas and fix
     vtime' accounting (for x86, this was already mostly correct but not
     entirely; for ARM, MIPS and RISC-V it wasn't)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: Use ERR_PTR_USR() to return -EFAULT as a __user pointer
  KVM: x86: Report deprecated x87 features in supported CPUID
  KVM: arm64: Workaround Cortex-A510's single-step and PAC trap errata
  KVM: arm64: Stop handle_exit() from handling HVC twice when an SError occurs
  KVM: arm64: Avoid consuming a stale esr value when SError occur
  RISC-V: KVM: Fix SBI implementation version
  RISC-V: KVM: make CY, TM, and IR counters accessible in VU mode
  kvm/riscv: rework guest entry logic
  kvm/arm64: rework guest entry logic
  kvm/x86: rework guest entry logic
  kvm/mips: rework guest entry logic
  kvm: add guest_state_{enter,exit}_irqoff()
  KVM: x86: Move delivery of non-APICv interrupt into vendor code
  kvm: Move KVM_GET_XSAVE2 IOCTL definition at the end of kvm.h

2 files changed, 112 insertions, 6 deletions

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 06912d6b39d0..f11039944c08 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -29,7 +29,9 @@
 #include <linux/refcount.h>
 #include <linux/nospec.h>
 #include <linux/notifier.h>
+#include <linux/ftrace.h>
 #include <linux/hashtable.h>
+#include <linux/instrumentation.h>
 #include <linux/interval_tree.h>
 #include <linux/rbtree.h>
 #include <linux/xarray.h>
@@ -368,8 +370,11 @@ struct kvm_vcpu {
 	u64 last_used_slot_gen;
 };
 
-/* must be called with irqs disabled */
-static __always_inline void guest_enter_irqoff(void)
+/*
+ * Start accounting time towards a guest.
+ * Must be called before entering guest context.
+ */
+static __always_inline void guest_timing_enter_irqoff(void)
 {
 	/*
 	 * This is running in ioctl context so its safe to assume that it's the
@@ -378,7 +383,18 @@ static __always_inline void guest_enter_irqoff(void)
 	instrumentation_begin();
 	vtime_account_guest_enter();
 	instrumentation_end();
+}
 
+/*
+ * Enter guest context and enter an RCU extended quiescent state.
+ *
+ * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is
+ * unsafe to use any code which may directly or indirectly use RCU, tracing
+ * (including IRQ flag tracing), or lockdep. All code in this period must be
+ * non-instrumentable.
+ */
+static __always_inline void guest_context_enter_irqoff(void)
+{
 	/*
 	 * KVM does not hold any references to rcu protected data when it
 	 * switches CPU into a guest mode. In fact switching to a guest mode
@@ -394,16 +410,79 @@ static __always_inline void guest_enter_irqoff(void)
 	}
 }
 
-static __always_inline void guest_exit_irqoff(void)
+/*
+ * Deprecated. Architectures should move to guest_timing_enter_irqoff() and
+ * guest_state_enter_irqoff().
+ */
+static __always_inline void guest_enter_irqoff(void)
+{
+	guest_timing_enter_irqoff();
+	guest_context_enter_irqoff();
+}
+
+/**
+ * guest_state_enter_irqoff - Fixup state when entering a guest
+ *
+ * Entry to a guest will enable interrupts, but the kernel state is interrupts
+ * disabled when this is invoked. Also tell RCU about it.
+ *
+ * 1) Trace interrupts on state
+ * 2) Invoke context tracking if enabled to adjust RCU state
+ * 3) Tell lockdep that interrupts are enabled
+ *
+ * Invoked from architecture specific code before entering a guest.
+ * Must be called with interrupts disabled and the caller must be
+ * non-instrumentable.
+ * The caller has to invoke guest_timing_enter_irqoff() before this.
+ *
+ * Note: this is analogous to exit_to_user_mode().
+ */
+static __always_inline void guest_state_enter_irqoff(void)
+{
+	instrumentation_begin();
+	trace_hardirqs_on_prepare();
+	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	instrumentation_end();
+
+	guest_context_enter_irqoff();
+	lockdep_hardirqs_on(CALLER_ADDR0);
+}
+
+/*
+ * Exit guest context and exit an RCU extended quiescent state.
+ *
+ * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is
+ * unsafe to use any code which may directly or indirectly use RCU, tracing
+ * (including IRQ flag tracing), or lockdep. All code in this period must be
+ * non-instrumentable.
+ */
+static __always_inline void guest_context_exit_irqoff(void)
 {
 	context_tracking_guest_exit();
+}
 
+/*
+ * Stop accounting time towards a guest.
+ * Must be called after exiting guest context.
+ */
+static __always_inline void guest_timing_exit_irqoff(void)
+{
 	instrumentation_begin();
 	/* Flush the guest cputime we spent on the guest */
 	vtime_account_guest_exit();
 	instrumentation_end();
 }
 
+/*
+ * Deprecated. Architectures should move to guest_state_exit_irqoff() and
+ * guest_timing_exit_irqoff().
+ */
+static __always_inline void guest_exit_irqoff(void)
+{
+	guest_context_exit_irqoff();
+	guest_timing_exit_irqoff();
+}
+
 static inline void guest_exit(void)
 {
 	unsigned long flags;
@@ -413,6 +492,33 @@ static inline void guest_exit(void)
 	local_irq_restore(flags);
 }
 
+/**
+ * guest_state_exit_irqoff - Establish state when returning from guest mode
+ *
+ * Entry from a guest disables interrupts, but guest mode is traced as
+ * interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
+ *
+ * 1) Tell lockdep that interrupts are disabled
+ * 2) Invoke context tracking if enabled to reactivate RCU
+ * 3) Trace interrupts off state
+ *
+ * Invoked from architecture specific code after exiting a guest.
+ * Must be invoked with interrupts disabled and the caller must be
+ * non-instrumentable.
+ * The caller has to invoke guest_timing_exit_irqoff() after this.
+ *
+ * Note: this is analogous to enter_from_user_mode().
+ */
+static __always_inline void guest_state_exit_irqoff(void)
+{
+	lockdep_hardirqs_off(CALLER_ADDR0);
+	guest_context_exit_irqoff();
+
+	instrumentation_begin();
+	trace_hardirqs_off_finish();
+	instrumentation_end();
+}
+
 static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
 {
 	/*
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index b46bcdb0cab1..5191b57e1562 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1624,9 +1624,6 @@ struct kvm_enc_region {
 #define KVM_S390_NORMAL_RESET	_IO(KVMIO,   0xc3)
 #define KVM_S390_CLEAR_RESET	_IO(KVMIO,   0xc4)
 
-/* Available with KVM_CAP_XSAVE2 */
-#define KVM_GET_XSAVE2		  _IOR(KVMIO,  0xcf, struct kvm_xsave)
-
 struct kvm_s390_pv_sec_parm {
 	__u64 origin;
 	__u64 length;
@@ -2048,4 +2045,7 @@ struct kvm_stats_desc {
 
 #define KVM_GET_STATS_FD  _IO(KVMIO,  0xce)
 
+/* Available with KVM_CAP_XSAVE2 */
+#define KVM_GET_XSAVE2		  _IOR(KVMIO,  0xcf, struct kvm_xsave)
+
 #endif /* __LINUX_KVM_H */